
    Z jI                         S r SSKJr  SSKJr  SSKJr  SSKJrJ	r	  \	R                  " \5      r\" SS9\ " S	 S
\5      5       5       rS
/rg)zMistral model configuration    )strict   )PreTrainedConfig)RopeParameters)auto_docstringloggingzmistralai/Mistral-7B-v0.1)
checkpointc                     ^  \ rS rSr% SrSrS/rSSSSSSSS.rS/S	/4S
S/S
/4S
/S
/4S.rSr	\
\S'   Sr\
\S'   Sr\
\S'   Sr\
\S'   Sr\
\S'   Sr\
\S'   Sr\
S-  \S'   Sr\\S'   Sr\
\S'   Sr\\S'   S r\\S!'   S"r\\S#'   Sr\
S-  \S$'   S%r\
S-  \S&'   S'r\
\\
   -  S-  \S('   S)r\\S*'   Sr\ \!-  S-  \S+'   Sr"\
S-  \S,'   S-r#\\
-  \S.'   U 4S/ jr$S0r%U =r&$ )1MistralConfig   a`  
Example:

```python
>>> from transformers import MistralModel, MistralConfig

>>> # Initializing a Mistral 7B style configuration
>>> configuration = MistralConfig()

>>> # Initializing a model from the Mistral 7B style configuration
>>> model = MistralModel(configuration)

>>> # Accessing the model configuration
>>> configuration = model.config
```mistralpast_key_valuescolwiserowwise)zlayers.*.self_attn.q_projzlayers.*.self_attn.k_projzlayers.*.self_attn.v_projzlayers.*.self_attn.o_projzlayers.*.mlp.gate_projzlayers.*.mlp.up_projzlayers.*.mlp.down_proj	input_idsinputs_embedshidden_statesattention_mask)embed_tokenslayersnormi }  
vocab_sizei   hidden_sizei 8  intermediate_size    num_hidden_layersnum_attention_heads   num_key_value_headsNhead_dimsilu
hidden_acti   max_position_embeddingsg{Gz?initializer_rangegư>rms_norm_epsT	use_cachepad_token_id   bos_token_id   eos_token_idFtie_word_embeddingsrope_parameterssliding_windowg        attention_dropoutc                   > U R                   b  U R                   OU R                  U R                  -  U l         U R                  c  U R                  U l        SU;   a  [        R                  S5        [        TU ]  " S0 UD6$ )Nlayer_typeszDetected Mistral model with layer_types. Consider using AutoModel or Ministral classes instead to enable alternating attention compatibility. )r    r   r   r   loggerwarning_oncesuper__post_init__)selfkwargs	__class__s     ڂ/root/GenerationalWealth/GenerationalWealth/venv/lib/python3.13/site-packages/transformers/models/mistral/configuration_mistral.pyr6   MistralConfig.__post_init__S   sv    )-)BHXHX\`\t\tHt##+'+'?'?D$F" ` w$.v..    )r    r   )'__name__
__module____qualname____firstlineno____doc__
model_typekeys_to_ignore_at_inferencebase_model_tp_planbase_model_pp_planr   int__annotations__r   r   r   r   r   r    r"   strr#   r$   floatr%   r&   boolr'   r)   r+   listr,   r-   r   dictr.   r/   r6   __static_attributes____classcell__)r9   s   @r:   r   r      sj     J#4"5 &/%.%.%."+ )"+ &(9:#%568IJ!"_$56 JK"s"s!!  HcDjJ#,S,#u#L%It#L#*# L#* +,L#S	/D(, %%48O^d*T18!%NC$J%%(us{(	/ 	/r<   r   N)rA   huggingface_hub.dataclassesr   configuration_utilsr   modeling_rope_utilsr   utilsr   r   
get_loggerr=   r3   r   __all__r2   r<   r:   <module>rU      s`    " . 3 1 , 
		H	% 67@/$ @/  8@/F 
r<   